File size: 4,718 Bytes
17ee76b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
"""This module contains transforms for videos."""

import numbers
import random

import numpy as np
from torchvision.transforms import RandomResizedCrop

from . import functional_video as F

__all__ = [
    "RandomResizedCropVideo",
    "CenterCropVideo",
    "NormalizeVideo",
    "ToTensorVideo",
    "RandomHorizontalFlipVideo",
]


class ResizeVideo:
    def __init__(self, size, interpolation_mode="bilinear"):
        self.size = size
        self.interpolation_mode = interpolation_mode

    def __call__(self, clip):
        return F.resize(clip, self.size, self.interpolation_mode)


class RandomResizedCropVideo(RandomResizedCrop):
    def __init__(

        self,

        size,

        crop,

        interpolation_mode="bilinear",

    ):
        if isinstance(size, tuple):
            assert len(size) == 2, "size should be tuple (height, width)"
            self.size = size
        else:
            self.size = (size, size)

        self.interpolation_mode = interpolation_mode
        self.crop = crop

    def __call__(self, clip):
        """

        Args:

            clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W)

        Returns:

            torch.tensor: randomly cropped/resized video clip.

                size is (C, T, H, W)

        """
        clip = F.resize(clip, self.size, self.interpolation_mode)
        # print(clip.shape)
        if clip.shape[2] - self.crop > 0:
            i = np.random.randint(clip.shape[2] - self.crop)
        else:
            i = 0
        if clip.shape[3] - self.crop > 0:
            j = np.random.randint(clip.shape[3] - self.crop)
        else:
            j = 0
        clip = clip[..., i : i + self.crop, j : j + self.crop]
        return clip

    def __repr__(self):
        return (
            self.__class__.__name__
            + f"(size={self.size}, interpolation_mode={self.interpolation_mode}, "
            + f"scale={self.scale}, ratio={self.ratio})"
        )


class CenterCropVideo:
    def __init__(self, crop_size):
        if isinstance(crop_size, numbers.Number):
            self.crop_size = (int(crop_size), int(crop_size))
        else:
            self.crop_size = crop_size

    def __call__(self, clip):
        """

        Args:

            clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W)

        Returns:

            torch.tensor: central cropping of video clip. Size is

            (C, T, crop_size, crop_size)

        """
        return F.center_crop(clip, self.crop_size)

    def __repr__(self):
        return self.__class__.__name__ + f"(crop_size={self.crop_size})"


class NormalizeVideo:
    """

    Normalize the video clip by mean subtraction and division by standard deviation

    Args:

        mean (3-tuple): pixel RGB mean

        std (3-tuple): pixel RGB standard deviation

        inplace (boolean): whether do in-place normalization

    """

    def __init__(self, mean, std, inplace=False):
        self.mean = mean
        self.std = std
        self.inplace = inplace

    def __call__(self, clip):
        """

        Args:

            clip (torch.tensor): video clip to be normalized. Size is (C, T, H, W)

        """
        return F.normalize(clip, self.mean, self.std, self.inplace)

    def __repr__(self):
        return (
            self.__class__.__name__
            + f"(mean={self.mean}, std={self.std}, inplace={self.inplace})"
        )


class ToTensorVideo:
    """Convert tensor data type from uint8 to float, divide value by 255.0 and

    permute the dimenions of clip tensor."""

    def __init__(self):
        pass

    def __call__(self, clip):
        """

        Args:

            clip (torch.tensor, dtype=torch.uint8): Size is (T, H, W, C)

        Return:

            clip (torch.tensor, dtype=torch.float): Size is (C, T, H, W)

        """
        return F.to_tensor(clip)

    def __repr__(self):
        return self.__class__.__name__


class RandomHorizontalFlipVideo:
    """

    Flip the video clip along the horizonal direction with a given probability

    Args:

        p (float): probability of the clip being flipped. Default value is 0.5

    """

    def __init__(self, p=0.5):
        self.p = p

    def __call__(self, clip):
        """

        Args:

            clip (torch.tensor): Size is (C, T, H, W)

        Return:

            clip (torch.tensor): Size is (C, T, H, W)

        """
        if random.random() < self.p:
            clip = F.hflip(clip)
        return clip

    def __repr__(self):
        return self.__class__.__name__ + f"(p={self.p})"